# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?P<Element><(?P<TagName>[:_A-z][-.0-9:_A-z\xB7]*)(?:[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*[\x09\x0A\x0D\x20]*=[\x09\x0A\x0D\x20]*(?:\"(?:[^<&\"]|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*\"|'(?:[^<&']|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*'))*[\x09\x0A\x0D\x20]*(?:>(?:(?:[^<&\]]|](?!]>))*(?:(?:(?P>Element)|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));|<!\[CDATA\[(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x5D]|](?!]>))*]]>|<\?[:_A-z][-.0-9:_A-z\xB7]*(?<!(?i:\?xml))(?:[\x09\x0A\x0D\x20]+(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x3F]|\?(?!>))*)?\?>|<!--(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x2D]|-(?!-))*-->)(?:[^<&\]]|](?!]>))*)*)<\/(?P=TagName)[\x09\x0A\x0D\x20]*|\/)>)|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));|<!\[CDATA\[(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x5D]|](?!]>))*]]>|<\?[:_A-z][-.0-9:_A-z\xB7]*(?<!(?i:\?xml))(?:[\x09\x0A\x0D\x20]+(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x3F]|\?(?!>))*)?\?>|<!--(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x2D]|-(?!-))*-->|<!DOCTYPE[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*(?:[\x09\x0A\x0D\x20]+(?:SYSTEM[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*')|PUBLIC[\x09\x0A\x0D\x20]+(?:\"[\x0A\x0D\x20\x21\x23-\x25\x27-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*\"|'[\x0A\x0D\x20\x21\x23-\x25\x28-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*')[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*')))?[\x09\x0A\x0D\x20]*(?:\[(?:(?:<!ELEMENT[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*[\x09\x0A\x0D\x20]+(?:EMPTY|ANY|\([\x09\x0A\x0D\x20]*#PCDATA(?:(?:[\x09\x0A\x0D\x20]*\|[\x09\x0A\x0D\x20]*[:_A-z][-.0-9:_A-z\xB7]*)*[\x09\x0A\x0D\x20]*\)\*|[\x09\x0A\x0D\x20]*\))|(?:(?P<choice>\([\x09\x0A\x0D\x20]*(?:[:_A-z][-.0-9:_A-z\xB7]*|(?P>choice)|(?P>seq))[?*+]?(?:[\x09\x0A\x0D\x20]*\|[\x09\x0A\x0D\x20]*(?:[:_A-z][-.0-9:_A-z\xB7]*|(?P>choice)|(?P>seq))[?*+]?)+[\x09\x0A\x0D\x20]*\))|(?P<seq>\([\x09\x0A\x0D\x20]*(?:[:_A-z][-.0-9:_A-z\xB7]*|(?P>choice)|(?P>seq))[?*+]?(?:[\x09\x0A\x0D\x20]*,[\x09\x0A\x0D\x20]*(?:[:_A-z][-.0-9:_A-z\xB7]*|(?P>choice)|(?P>seq))[?*+]?)*[\x09\x0A\x0D\x20]*\)))[?*+]?)[\x09\x0A\x0D\x20]*>|<!ATTLIST[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*(?:[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*[\x09\x0A\x0D\x20]+(?:CDATA|(?:ID(?:REFS?)?|ENTIT(?:Y|IES)|NMTOKENS?)|(?:NOTATION[\x09\x0A\x0D\x20]+\([\x09\x0A\x0D\x20]*[:_A-z][-.0-9:_A-z\xB7]*(?:[\x09\x0A\x0D\x20]*\|[\x09\x0A\x0D\x20]*[:_A-z][-.0-9:_A-z\xB7]*)*[\x09\x0A\x0D\x20]*\)|\([\x09\x0A\x0D\x20]*(?:[-.0-9:_A-z\xB7])+(?:[\x09\x0A\x0D\x20]*\|[\x09\x0A\x0D\x20]*(?:[-.0-9:_A-z\xB7])+)*[\x09\x0A\x0D\x20]*\)))[\x09\x0A\x0D\x20]+(?:#(?:REQUIRED|IMPLIED)|(?:#FIXED[\x09\x0A\x0D\x20]+)?(?:\"(?:[^<&\"]|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*\"|'(?:[^<&']|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*')))*[\x09\x0A\x0D\x20]*>|(?:<!ENTITY[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*[\x09\x0A\x0D\x20]+(?:(?:\"(?:[^%&\"]|%[:_A-z][-.0-9:_A-z\xB7]*;|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*\"|'(?:[^%&']|%[:_A-z][-.0-9:_A-z\xB7]*;|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*')|(?:SYSTEM[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*')|PUBLIC[\x09\x0A\x0D\x20]+(?:\"[\x0A\x0D\x20\x21\x23-\x25\x27-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*\"|'[\x0A\x0D\x20\x21\x23-\x25\x28-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*')[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*'))(?:[\x09\x0A\x0D\x20]+NDATA[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*)?)[\x09\x0A\x0D\x20]*>|<!ENTITY[\x09\x0A\x0D\x20]+%[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*[\x09\x0A\x0D\x20]+(?:(?:\"(?:[^%&\"]|%[:_A-z][-.0-9:_A-z\xB7]*;|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*\"|'(?:[^%&']|%[:_A-z][-.0-9:_A-z\xB7]*;|&(?:[:_A-z][-.0-9:_A-z\xB7]*|#(?:[0-9]+|x[0-9a-fA-F]+));)*')|(?:SYSTEM[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*')|PUBLIC[\x09\x0A\x0D\x20]+(?:\"[\x0A\x0D\x20\x21\x23-\x25\x27-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*\"|'[\x0A\x0D\x20\x21\x23-\x25\x28-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*')[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*')))[\x09\x0A\x0D\x20]*>)|<!NOTATION[\x09\x0A\x0D\x20]+[:_A-z][-.0-9:_A-z\xB7]*[\x09\x0A\x0D\x20]+(?:(?:SYSTEM[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*')|PUBLIC[\x09\x0A\x0D\x20]+(?:\"[\x0A\x0D\x20\x21\x23-\x25\x27-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*\"|'[\x0A\x0D\x20\x21\x23-\x25\x28-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*')[\x09\x0A\x0D\x20]+(?:\"[^\"]*\"|'[^']*'))|PUBLIC[\x09\x0A\x0D\x20]+(?:\"[\x0A\x0D\x20\x21\x23-\x25\x27-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*\"|'[\x0A\x0D\x20\x21\x23-\x25\x28-\x2F\x3A\x3B\x3D\x3F\x40_0-9A-z]*'))[\x09\x0A\x0D\x20]*>|<\?[:_A-z][-.0-9:_A-z\xB7]*(?<!(?i:\?xml))(?:[\x09\x0A\x0D\x20]+(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x3F]|\?(?!>))*)?\?>|<!--(?:[^\x01-\x08\x0B\x0C\x0E-\x1F\x2D]|-(?!-))*-->)|(?:%[:_A-z][-.0-9:_A-z\xB7]*;|[\x09\x0A\x0D\x20]+))*][\x09\x0A\x0D\x20]*)?>"
test_str = ("<appointments>\n"
" <event date=\"03-05-02\" start-time=\"09:00\" end-time=\"10:00\">\n"
" <type>Meeting</type>\n"
" <title>Staff Meeting</title>\n"
" <description>Weekly staff meeting</description>\n"
" <location>Conference Room</location>\n"
" <reminder status=\"no\"/>\n"
" </event>\n\n"
" <event date=\"03-06-02\" start-time=\"14:00\" end-time=\"15:00\">\n"
" <type>Interview</type>\n"
" <title>Developer Interview</title>\n"
" <description>Interview new developer candidate.</description>\n"
" <location>Office</location>\n"
" <reminder status=\"yes\" interval=\"15-min\" method=\"ICQ\"/>\n"
" </event>\n\n"
" <event date=\"03-15-02\" start-time=\"13:45\" end-time=\"15:00\">\n"
" <type>Dentist</type>\n"
" <title>Root Canal</title>\n"
" <description>Root canal on lower left molar.</description>\n"
" <location>Dr. Scrivello's Office</location>\n"
" <reminder status=\"yes\" interval=\"1-day\" method=\"e-mail\"/>\n"
" </event>\n"
"</appointments>")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html